Case study

A 25M-user edutainment app

$100M+ ARR · 100M downloads

How category-level personalization lifted notification CTR +43% and doubled second-video starts

In six weeks, Pavo took the app's sticky notifications from broadcast logic to category-level personalization, lifting engagement across the full funnel, from click to second-video start, and deepening the retention a subscription business runs on.

Monthly active users
25M
Downloads
100M
Annual recurring revenue
$100M+
Surface personalized
Notifications
  • +43%Notification CTR
  • +94%Second-video initiation
  • +27%70% video completion
  • +23%40% video completion

The problem

The app's notifications ran on a broadcast model: the same four daily pushes, 7, 9, 11 AM and 1 PM, to everyone, chosen from a handful of manual and query-driven sources.

Pavo found the ranking query counted views driven by earlier notifications, a self-reinforcing loop, and organized content into three business units (Awareness, Income, Skill) on the content side only. On the audience side there was no segmentation at all.

The symptom was a plateauing click-through rate around 1.27%. But this wasn't a content-quality problem, the app's library has strong organic engagement, it was a matching problem: the right content existed, it just wasn't reaching the right users. In a subscription business, every day a user doesn't find value is a day closer to churn.

  • 01Content-manager requests
  • 02Event-driven manual picks, breaking news, trending topics, seasonal events
  • 03A query ranking content by total watch hours per business unit
Getting a high CTR is easy, maybe by sending clickbaity notifications. That's why I want to track a more holistic metric: not just get the user on the platform, but let them consume the content.
Director of Content OperationsEdutainment app

The approach

Pavo's principle: start with the broadest segmentation that could show lift in week one, validate it rigorously, build trust, then go deeper.

  1. 01

    Compiled the tribal knowledge

    Pavo connected to the app's warehouse and mapped every table in the notification pipeline, content metadata, user profiles, video-play tables, MoEngage campaign data, and funnel tables, into a complete operational model, and reviewed the daily ranking queries. That surfaced the structural issues silently capping performance: the self-reinforcing notification loop, and organic signals drowned out by notification-driven views.

  2. 02

    Designed the content-selection logic

    With a mandate to power half the notification slots, Pavo built new selection logic: one slot for proven organic performers (evergreen content up to 120 days old), one for fresh, trending content. Both replaced raw view counts with a quality-weighted score across intent, completion depth, and second-video likelihood, plus category-diversity multipliers, saturation penalties, and organic-only counting.

  3. 03

    Ramped up in phases

    Phase 1 (3 weeks): a 50/50 A/B matching each user to their primary interest group, Awareness, Income, Skill, or English, with two slots held as concurrent controls. Phase 2 (3 weeks): reclassify users into 16 category-level segments learned from watch behavior, and roll out to 100% of users across the 9 AM and 1 PM slots.

The results

From click to second-video start, every stage moved, and the deeper the funnel stage, the larger the lift.

  • Notification CTR+43%
  • Second-video initiation+94%
  • 70% video completion+27%
  • 40% video completion+23%
  • Click → 5s watched+18%

CTR climbed the ladder from a 1.27% broadcast baseline to 1.65% with interest-group personalization to 1.82% at category level.

Engagement depth

Funnel stageBroadcastPhase 1Phase 2Lift vs broadcast
Click → 5s watched30.5%32.4%36.1%+18%
40% video completion33.0%39.6%40.6%+23%
70% video completion24.5%29.8%31.1%+27%
2nd-video initiation10.7%13.8%20.7%+94%
We've seen a good jump in numbers and we've been able to maintain them in a stable way. The category-level bifurcation we did is the right spot.
DGM, Content Strategy & OperationsEdutainment app

What's next

PhaseWhat it is
Phase 0 · Broadcast (historical)Same content to all users
Phase 1 · Interest-group segments4 interest groups, group-level content; ranked by watch hours
Phase 2 · Category segments (current)16 category-based groups; ranked by deeper engagement metrics
Phase 3 · Per-user rulesIndividual content from user intelligence (lifecycle, responsiveness, preference) and content intelligence (collaborative filtering, dedup, continuity)
Phase 4 · Per-user predictionsML models rank content per user by predicted engagement; collaborative filtering becomes model-informed
Phase 5 · Self-learningAdaptive exploration and weekly retraining; the system improves autonomously from feedback

In closing

In six weeks Pavo mapped the notification system, found the structural flaws capping it, designed new quality-weighted selection logic, and ran a phased A/B program from interest groups to 16 category clusters, moving every stage of the funnel while holding CTR gains stable. The next target state is user-level, self-learning personalization above the cluster layer.